| From: | Itagaki Takahiro <itagaki(dot)takahiro(at)gmail(dot)com> |
|---|---|
| To: | Greg Stark <stark(at)mit(dot)edu> |
| Cc: | pgsql-hackers(at)postgresql(dot)org |
| Subject: | Re: Adding getrusage profiling data to EXPLAIN output |
| Date: | 2010-10-01 01:51:41 |
| Message-ID: | AANLkTin_Le9EoBVu-eJjvaMg_vcCJVAKcfnNMCuMB3Fj@mail.gmail.com |
| Views: | Raw Message | Whole Thread | Download mbox | Resend email |
| Thread: | |
| Lists: | pgsql-hackers |
On Fri, Oct 1, 2010 at 9:16 AM, Greg Stark <stark(at)mit(dot)edu> wrote:
> Attached is a patch to display getrusage output to EXPLAIN output.
> This is the patch I mentioned previously in
> http://archives.postgresql.org/pgsql-hackers/2010-02/msg00684.php and
> it raises the same issues we were talking about then.
How much overhead do you have with "resource" option?
getrusage() calls for each tuple might have considerable overheads.
How much difference between (analyze) and (analyze, resource) options?
Auto_explain and pg_stat_statements will be also adjusted to the change
when the patch is acceptable, I was asked for "queries ordered by CPU times"
in pg_stat_statements several times. The getrusage infrastructure will
make it a real possibility.
--
Itagaki Takahiro
| From | Date | Subject | |
|---|---|---|---|
| Next Message | Robert Haas | 2010-10-01 02:20:48 | Re: I: About "Our CLUSTER implementation is pessimal" patch |
| Previous Message | Greg Smith | 2010-10-01 01:32:38 | Re: Postgres vs. intel ccNUMA on Linux |